Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

A breakdown of my recent personal project! Software used: Blender, Houdini, Liquigen, Gaea, Ae, Ps. Models and tools: Quixel, BigMediumSmall, Polyganiq, Geo-Scatter, Fox Renderfarm, Neat Video Denoiser, Mixamo.

Zertox3D's profile picture

Dylan Donaldson

5,526 subscribers

107,502 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Dylan Donaldson
Dylan Donaldsonvor 2 Jahren

Full quality:

Profilbild von ibotpl
ibotplvor 2 Jahren

impressive breakdown!! amazing work, well done.

Profilbild von Dylan Donaldson
Dylan Donaldsonvor 2 Jahren

🔥 music is 'used2' by @hxly_xo

Profilbild von Jimmy Edward Films
Jimmy Edward Filmsvor 2 Jahren

Zertox… Holy hell phenomenal work brother

Profilbild von Nassos Y 🇵🇸
Nassos Y 🇵🇸vor 2 Jahren

This is gorgeous 😍

Profilbild von Dylan Donaldson
Dylan Donaldsonvor 2 Jahren

Thank you <33

Profilbild von Birchgo
Birchgovor 2 Jahren

This is beautiful!

Profilbild von Dylan Donaldson
Dylan Donaldsonvor 2 Jahren

Thank you so much!

Profilbild von Caze
Cazevor 2 Jahren

amazing!

Profilbild von Dylan Donaldson
Dylan Donaldsonvor 2 Jahren

Thanks Caze!

Ähnliche Videos

Check out VFX artist Intae Jang's technical breakdown of magical energy destroying a house, created in Houdini and Blender as a personal project Watch the full video in Intae Jang's Behance gallery: #VFX #VFXbreakdown #simulation #B3D #Blender #Houdini
0:28

Check out VFX artist Intae Jang's technical breakdown of magical energy destroying a house, created in Houdini and Blender as a personal project Watch the full video in Intae Jang's Behance gallery: #VFX #VFXbreakdown #simulation #B3D #Blender #Houdini

CG Channel

12,190 Aufrufe • vor 1 Jahr

Hi everyone, I'm so excited to share the CGI breakdown of my animation, 「Aurora Project I」!!! This video showcases the details of my first 3D character, the custom shader I created, and the FX made in Houdini. Hope you'll enjoy it! #animation #b3d #blender #3DCG #breakdown
1:56

Hi everyone, I'm so excited to share the CGI breakdown of my animation, 「Aurora Project I」!!! This video showcases the details of my first 3D character, the custom shader I created, and the FX made in Houdini. Hope you'll enjoy it! #animation #b3d #blender #3DCG #breakdown

ArKus⚡@Art&3DCG

16,491 Aufrufe • vor 1 Jahr

I used 𝚏𝚡 to build Mini, a personal web browser. Many times I need to screen share, stream, or just test something without the 'bloat' and state of my browser. So I go Mini. This was a cool test for and open models. It was the first time I experienced how cheap, but also how *good* these things can be. 'Personal software' is a hot topic. "I spent $25,000USD to cancel my $10 XYZ subscription" is a real thing 😂 (especially in Enterprises these days). But I think open and local models will change this dynamic very profoundly. Software will really become spontaneous. ps: shoutout to Orion browser who inspired me with 'focus mode'. I wanted my browser to be even more minimal, hackable, and run on Chromium.
0:41

I used 𝚏𝚡 to build Mini, a personal web browser. Many times I need to screen share, stream, or just test something without the 'bloat' and state of my browser. So I go Mini. This was a cool test for and open models. It was the first time I experienced how cheap, but also how *good* these things can be. 'Personal software' is a hot topic. "I spent $25,000USD to cancel my $10 XYZ subscription" is a real thing 😂 (especially in Enterprises these days). But I think open and local models will change this dynamic very profoundly. Software will really become spontaneous. ps: shoutout to Orion browser who inspired me with 'focus mode'. I wanted my browser to be even more minimal, hackable, and run on Chromium.

Guillermo Rauch

93,128 Aufrufe • vor 1 Tag

this GTA style ad that i made for whop generated millions of views... i made a full breakdown video on how i created it for anyone interested it includes: - my editing process - AI tools used - my overall approach/thesis on these kinds of videos if you want the full guide, reply “YES” + RT and I’ll DM it to you (must be following)
0:41

this GTA style ad that i made for whop generated millions of views... i made a full breakdown video on how i created it for anyone interested it includes: - my editing process - AI tools used - my overall approach/thesis on these kinds of videos if you want the full guide, reply “YES” + RT and I’ll DM it to you (must be following)

beech

86,900 Aufrufe • vor 9 Monaten

I'm genuinely blown away by this. The leap from text descriptions straight to 3D models? It's next-level. Think about the possibility: a stream of prompts turns into a treasure trove of 3D pieces. Gather them, and you've got a full scene ready to come to life. The thought alone was exciting, but seeing it in action? Mind-bending. Take user 'NeonGlitch86' for instance. They've crafted an entire miniature world using nothing but Luma AI's #Genie text-to-3D tool combined with Blender's magic. "Totally geeking out with Luma AI. Today's project was a scene built from scratch with generated 3D models. Slapped some Mixamo rigs onto my characters and placed them into Blender. It's like a playground for bringing scene sketches to life." - NeonGlitch86
1:00

I'm genuinely blown away by this. The leap from text descriptions straight to 3D models? It's next-level. Think about the possibility: a stream of prompts turns into a treasure trove of 3D pieces. Gather them, and you've got a full scene ready to come to life. The thought alone was exciting, but seeing it in action? Mind-bending. Take user 'NeonGlitch86' for instance. They've crafted an entire miniature world using nothing but Luma AI's #Genie text-to-3D tool combined with Blender's magic. "Totally geeking out with Luma AI. Today's project was a scene built from scratch with generated 3D models. Slapped some Mixamo rigs onto my characters and placed them into Blender. It's like a playground for bringing scene sketches to life." - NeonGlitch86

Linus ✦ Ekenstam

696,171 Aufrufe • vor 2 Jahren

Introducing "Mine Like A Chad" an entirely AI generated commercial for Tari Every single shot, every sound effect, the music, even the vfx are all AI generated. Breakdown of tools I used: Midjourney & Chat GPT - Image gen and Image editing Topaz Gigapixel - Image Upscale Kling, Luma & Higgsfield - Image to Video and VFX Eleven Labs - Sound Effects Udio - Music generation Davinci Resolve - Editing and Color Grade Huge shoutout to @RealJonahBlake and his Real agency for being amazing partners on this project and helping me out so much.
0:49

Introducing "Mine Like A Chad" an entirely AI generated commercial for Tari Every single shot, every sound effect, the music, even the vfx are all AI generated. Breakdown of tools I used: Midjourney & Chat GPT - Image gen and Image editing Topaz Gigapixel - Image Upscale Kling, Luma & Higgsfield - Image to Video and VFX Eleven Labs - Sound Effects Udio - Music generation Davinci Resolve - Editing and Color Grade Huge shoutout to @RealJonahBlake and his Real agency for being amazing partners on this project and helping me out so much.

Kyle Salazar

11,343 Aufrufe • vor 1 Jahr

I had to do this of course - test out the new Google Omni Flash model with my favorite 3d art sandbox - Dreams. Just a quick test for now.. I'll be sharing more examples and techniques soon but wanted to show you this one. There's something very fitting about combining "handmade" 3d models and animations sculpted from scratch in software that runs on 2013 hardware, with some of the most advanced AI technology in the world. As part of my work for Google, I've used Google V2V models on a few different projects now - Ancestra, Dear Upstairs Neighbors and most recently one of the IO films (I'll share more about that project soon) 🥰 - and video continues to be my favorite form of input for Generative Ai workflows. If an image says more than a thousand words, a video says more than a million. And knowing that these capabilities are now in the hands of all of you, makes me very excited to see the new workflows and projects that will come out of it. What do you think of Omni so far?
0:45

I had to do this of course - test out the new Google Omni Flash model with my favorite 3d art sandbox - Dreams. Just a quick test for now.. I'll be sharing more examples and techniques soon but wanted to show you this one. There's something very fitting about combining "handmade" 3d models and animations sculpted from scratch in software that runs on 2013 hardware, with some of the most advanced AI technology in the world. As part of my work for Google, I've used Google V2V models on a few different projects now - Ancestra, Dear Upstairs Neighbors and most recently one of the IO films (I'll share more about that project soon) 🥰 - and video continues to be my favorite form of input for Generative Ai workflows. If an image says more than a thousand words, a video says more than a million. And knowing that these capabilities are now in the hands of all of you, makes me very excited to see the new workflows and projects that will come out of it. What do you think of Omni so far?

Martin Nebelong

38,451 Aufrufe • vor 3 Monaten

Introducing “The Last Ember” - An AI Film Trailer This is the trailer of a longer AI film I’ve been working on for the past month. It’s a project deeply personal to me, inspired by a true story from my own life. I’ve carried this idea for years, but the high cost of traditional filmmaking made it seem impossible. Now, with today’s AI tools, creating feature films is within reach. It still takes countless hours of refining, but what felt like a distant dream is finally becoming a reality. Tools Used: • Image: Freepik, Midjourney, Ideogram • Video: Hailuo AI (MiniMax), Kling AI • Lipsync: Kling AI • Upscaling: Magnific.ai • Voice: ChatGPT Advanced Voice Thank you for watching. The Last Ember represents a new era of storytelling, one where anyone with a story can share it with the world.
0:36

Introducing “The Last Ember” - An AI Film Trailer This is the trailer of a longer AI film I’ve been working on for the past month. It’s a project deeply personal to me, inspired by a true story from my own life. I’ve carried this idea for years, but the high cost of traditional filmmaking made it seem impossible. Now, with today’s AI tools, creating feature films is within reach. It still takes countless hours of refining, but what felt like a distant dream is finally becoming a reality. Tools Used: • Image: Freepik, Midjourney, Ideogram • Video: Hailuo AI (MiniMax), Kling AI • Lipsync: Kling AI • Upscaling: Magnific.ai • Voice: ChatGPT Advanced Voice Thank you for watching. The Last Ember represents a new era of storytelling, one where anyone with a story can share it with the world.

el.cine

39,007 Aufrufe • vor 1 Jahr

Of course, The Jakarta Globe asked me how I see AI tools influencing newsrooms — both in terms of opportunities and risks. AI is both enormously helpful and unpredictably dangerous. On the one hand, it significantly accelerates many newsroom processes, from interview transcription and video editing to translation and event planning. On the other hand, it has never been easier to fall victim to fake images and manipulated footage, particularly in a 24-hour news environment. Today, these tools are accessible to almost everyone, giving them the ability to influence narratives far beyond their place of origin. We have been working with artificial intelligence technologies for several years. Initially, we used Western models, but we are actively developing our own. Our team enjoys experimenting with these tools. For example, we created a project in which President Putin delivers his famous speeches, including the Munich speech, in English using his own AI-generated voice. The result is remarkably difficult to distinguish from the original.
3:09

Of course, The Jakarta Globe asked me how I see AI tools influencing newsrooms — both in terms of opportunities and risks. AI is both enormously helpful and unpredictably dangerous. On the one hand, it significantly accelerates many newsroom processes, from interview transcription and video editing to translation and event planning. On the other hand, it has never been easier to fall victim to fake images and manipulated footage, particularly in a 24-hour news environment. Today, these tools are accessible to almost everyone, giving them the ability to influence narratives far beyond their place of origin. We have been working with artificial intelligence technologies for several years. Initially, we used Western models, but we are actively developing our own. Our team enjoys experimenting with these tools. For example, we created a project in which President Putin delivers his famous speeches, including the Munich speech, in English using his own AI-generated voice. The result is remarkably difficult to distinguish from the original.

Margarita Simonyan

21,786 Aufrufe • vor 11 Tagen

I've used basically every knowledge management and project management tool out there, and every tool has the same problem. they expect me to do things that computers should do. meanwhile, so many AI tools replace the wrong work. i want to do more creative work, less administrative work. the right tool SHOULD assist me at doing my best work. but no tool has ever done that for me! so here's the first public demo of my dream solution to both problems, in the form of deeply personalized software. i've had so much fun building this, and it's already had a materially positive impact on my life. would love to share more, so ask questions and I'll go deeper into how various parts of the system work under the hood!
49:36

I've used basically every knowledge management and project management tool out there, and every tool has the same problem. they expect me to do things that computers should do. meanwhile, so many AI tools replace the wrong work. i want to do more creative work, less administrative work. the right tool SHOULD assist me at doing my best work. but no tool has ever done that for me! so here's the first public demo of my dream solution to both problems, in the form of deeply personalized software. i've had so much fun building this, and it's already had a materially positive impact on my life. would love to share more, so ask questions and I'll go deeper into how various parts of the system work under the hood!

📙 Alex Hillman

47,462 Aufrufe • vor 8 Monaten

BLACK SUN - AI Trailer I’m truly excited to finally show you my most ambitious AI video project yet. I’m sharing the process, prompts, and tools I used in the comments👇🧵 Synopsis An ancient spherical relic, long dormant over a desert planet, suddenly awakens—triggering a plague that decimates most life while transforming a few into strange, evolved beings. In the absence of the tyrant who once ruled, chaos erupts: warring tribes, Starborn visitors from far-off worlds, and rival factions arise—some dedicated to preserving the relic, others bent on its destruction.
2:48

BLACK SUN - AI Trailer I’m truly excited to finally show you my most ambitious AI video project yet. I’m sharing the process, prompts, and tools I used in the comments👇🧵 Synopsis An ancient spherical relic, long dormant over a desert planet, suddenly awakens—triggering a plague that decimates most life while transforming a few into strange, evolved beings. In the absence of the tyrant who once ruled, chaos erupts: warring tribes, Starborn visitors from far-off worlds, and rival factions arise—some dedicated to preserving the relic, others bent on its destruction.

karim_yourself

92,317 Aufrufe • vor 1 Jahr

Konnech isn't just another tech firm. It's a CCP-linked operation building the tools that help rig elections in the U.S. and Australia. Konnech is a Michigan-based election logistics software company founded by Chinese-born Eugene Yu, and is effectively a Communist China software company with deep CCP ties. Konnech's Chinese subsidiary, Jinhua Yulian Network Technology / Yulian Network, developed the election management software used in the U.S. The same Chinese subsidiary simultaneously developed election software for the Chinese Communist Party itself. Sensitive personal data on American poll workers was sent to, stored on, or accessible by developers and contractors in China, in violation of contracts requiring US-only handling. This creates a direct backdoor and security risk allowing Chinese Communist influence or manipulation over U.S. election processes, poll-worker management, logistics, scheduling, building schematics, election workers all throughout the U.S. The company's Australian operations, Konnech Australia, extend the same compromised software and influence into Australian elections. The real-world fallout referenced in the broader reporting around this period came in the 2022 arrest of Konnech CEO Eugene Yu by Los Angeles County prosecutors over alleged improper transfer of poll-worker data to China, the charges were later dropped. There is no coincidence that while Biden was in office that the charges were dropped, especially when we know now from the recent declassified documents that China was interfering in our elections and helping Biden in the 2020 election.
5:02

Konnech isn't just another tech firm. It's a CCP-linked operation building the tools that help rig elections in the U.S. and Australia. Konnech is a Michigan-based election logistics software company founded by Chinese-born Eugene Yu, and is effectively a Communist China software company with deep CCP ties. Konnech's Chinese subsidiary, Jinhua Yulian Network Technology / Yulian Network, developed the election management software used in the U.S. The same Chinese subsidiary simultaneously developed election software for the Chinese Communist Party itself. Sensitive personal data on American poll workers was sent to, stored on, or accessible by developers and contractors in China, in violation of contracts requiring US-only handling. This creates a direct backdoor and security risk allowing Chinese Communist influence or manipulation over U.S. election processes, poll-worker management, logistics, scheduling, building schematics, election workers all throughout the U.S. The company's Australian operations, Konnech Australia, extend the same compromised software and influence into Australian elections. The real-world fallout referenced in the broader reporting around this period came in the 2022 arrest of Konnech CEO Eugene Yu by Los Angeles County prosecutors over alleged improper transfer of poll-worker data to China, the charges were later dropped. There is no coincidence that while Biden was in office that the charges were dropped, especially when we know now from the recent declassified documents that China was interfering in our elections and helping Biden in the 2020 election.

The SCIF

15,566 Aufrufe • vor 1 Monat

Yesterday Claude filed my overdue German VAT Tax statements for Q3 2025. I used Claude Cowork and the Claude Chrome extension, no programming tricks, completely off the shelf stuff from Anthropic. I started Cowork with a project folder and put pdfs of my invoices and receipts in there and asked it to prepare the accounts for each quarter. Then I logged in to the German tax portal (Elster) and asked it to find and fill out the relevant forms and submit them. I recorded the last part of the process, then asked Claude to redact my personal information from the video and speed it up 3x so I could share it. Here it is, Claude does my taxes, Germany edition
3:07

Yesterday Claude filed my overdue German VAT Tax statements for Q3 2025. I used Claude Cowork and the Claude Chrome extension, no programming tricks, completely off the shelf stuff from Anthropic. I started Cowork with a project folder and put pdfs of my invoices and receipts in there and asked it to prepare the accounts for each quarter. Then I logged in to the German tax portal (Elster) and asked it to find and fill out the relevant forms and submit them. I recorded the last part of the process, then asked Claude to redact my personal information from the video and speed it up 3x so I could share it. Here it is, Claude does my taxes, Germany edition

Andrew Jefferson

205,878 Aufrufe • vor 6 Monaten

I used to think waiting for my PC to finish a task was just part of the creative process. Then I realized how much time I was wasting just sitting around and checking on it. 😅 AI video generations, 4K exports, Blender renders, model training, code builds, huge downloads… some of these tasks can easily run for 30–40+ minutes. And somehow, I’d still walk over to my computer every few minutes like staring at the progress bar would make it move faster. 😂 That’s where StarDesk changed my workflow. Now I can access and monitor my desktop directly from my phone, even when I’m away from my setup. I can: 📱 Check AI video generations 🎬 Monitor exports and renders 🧠 Keep an eye on AI/model training 🔄 Restart workflows when something goes wrong 📂 Access files and desktop applications ⚡ Start the next task without being at my desk 💻 Monitor scripts, builds, and long-running processes And it’s not just useful for AI creators. 🎨 3D Artists: Keep track of Blender, Unreal Engine, Maya, Cinema 4D, and Houdini renders. 💻 Developers: Monitor builds, scripts, deployments, and local servers. 📸 Photographers: Check Lightroom exports and large file imports. 🎮 Gamers: Start downloads, manage updates, and get everything ready before you’re back home. 🎓 Students & Professionals: Access important desktop files and applications from wherever you are. 🏢 Small Businesses: Stay connected to office files and essential desktop tools while away. 🛠️ IT Support: Remotely access and troubleshoot computers without being physically there. The biggest difference? Your computer can keep doing the heavy work while you get on with your life. I originally tried StarDesk because it was free. I thought I’d only use it for checking my AI video workflows. Turns out, it became one of those small tools that quietly became part of my everyday workflow. Sometimes the best productivity tools aren’t the ones with the biggest feature lists. They’re the ones that simply give you more control, less waiting, and more freedom to step away from your desk. Try StarDesk 👇 #StarDesk #RemoteDesktop #AI #Productivity #AITools
0:40

I used to think waiting for my PC to finish a task was just part of the creative process. Then I realized how much time I was wasting just sitting around and checking on it. 😅 AI video generations, 4K exports, Blender renders, model training, code builds, huge downloads… some of these tasks can easily run for 30–40+ minutes. And somehow, I’d still walk over to my computer every few minutes like staring at the progress bar would make it move faster. 😂 That’s where StarDesk changed my workflow. Now I can access and monitor my desktop directly from my phone, even when I’m away from my setup. I can: 📱 Check AI video generations 🎬 Monitor exports and renders 🧠 Keep an eye on AI/model training 🔄 Restart workflows when something goes wrong 📂 Access files and desktop applications ⚡ Start the next task without being at my desk 💻 Monitor scripts, builds, and long-running processes And it’s not just useful for AI creators. 🎨 3D Artists: Keep track of Blender, Unreal Engine, Maya, Cinema 4D, and Houdini renders. 💻 Developers: Monitor builds, scripts, deployments, and local servers. 📸 Photographers: Check Lightroom exports and large file imports. 🎮 Gamers: Start downloads, manage updates, and get everything ready before you’re back home. 🎓 Students & Professionals: Access important desktop files and applications from wherever you are. 🏢 Small Businesses: Stay connected to office files and essential desktop tools while away. 🛠️ IT Support: Remotely access and troubleshoot computers without being physically there. The biggest difference? Your computer can keep doing the heavy work while you get on with your life. I originally tried StarDesk because it was free. I thought I’d only use it for checking my AI video workflows. Turns out, it became one of those small tools that quietly became part of my everyday workflow. Sometimes the best productivity tools aren’t the ones with the biggest feature lists. They’re the ones that simply give you more control, less waiting, and more freedom to step away from your desk. Try StarDesk 👇 #StarDesk #RemoteDesktop #AI #Productivity #AITools

Nancy Diazz

50,688 Aufrufe • vor 11 Tagen

My fox shooting garden defending AI robot is finally done and WORKING! 🤩 (Don’t worry it only shoots 💦 water) After months of slowly moving forward with each part I finished the last step to train a TensorFlow model on the footage of the 🦊 fox I collected hours of footage 📹 with the fox roaming around my garden, from this I labeled around 2000 images with the fox by hand ✋ Honestly, I was quite skeptical training the model was actually gonna work, maybe this was partly the reason I avoided working on this until the very end. If I couldn’t train a model to detect the fox, this whole robot would never be able to function properly. On the flipside though, with no previous experience in hardware or electronics there was a bit of a learning curve and I didn’t want to end up labeling thousands of images, training a TensorFlow model, only to fail on building the hardware. As I started building, I realized that mixing hardware and software adds quite another dimension to debugging things. At times I wasted hours debugging code in my IDE, only to realize the issue was somewhere in the electronics. Furthermore, combining this side project with a full time job and a young family, is not always easy. It can be quite frustrating, to know you only need 4 hours of concentrated effort for a small task, having to spread it out across a week of 20min increments. Then, a few months into the build I noticed the fox had stopped coming to my garden, in fact one day, I recorded her walking with 3 cute little 🐶 pups, and the next day I saw her moving out of my garden completely. Did she know I was building a robot? I had this strange mix of feelings, happy my garden was safe from poop and digging, happy she was safe with her pups, but how was I gonna finish this project if my robot had no fox to detect? For sure they would be back next year, I figured I could postpone the whole thing until next winter, but I also knew it was gonna be much harder to pick up momentum if I did let it sit there for six months. So I decided to keep working, hoping the fox would reappear,.. but she never did. As I finished labeling the footage and started training my model, I could finally see the mAP results, quantifying the precision of my object detection model. It was measuring at 78% across different metrics on detecting my fox. I quickly ran the model on some of the video footage I got from my fox. Inference speed took a hit, but it did a near perfect job detecting the fox, even when she was deep down in the grass or wizzing past in a motion blur. It took me by surprise how well it worked. With the default model I had to drop my confidence threshold way down to 15%, to recognize the fox as 🦜“bird” in one or two frames, with my custom model it followed the fox all the way down to the back of the garden! Still this didn’t solve the issue of there being no actual fox in my garden and how was I gonna wrap this project in a short timeframe. I played with the idea of putting a fox toy 🧸 on an RC 🚗 car, or borrowing a dog to run around the garden to test. Friends suggested I run around the garden in a fox costume.. what a ridiculous idea. I wasn’t really feeling the idea of running around the garden in a floppy cloth fox 🎭 costume, but had a look anyway. I came across these self inflating costumes. This actually could be perfect. Since it’s inflated, it would hold its shape super well, making it much easier to label, train and be recognized by my robot. So I got the costume and shot a time lapse of myself as a fox walking around the garden. I labeled it to around 600 images. Ran the model training again and got a mAP result of 82%. This was even better than my real fox! At this point I knew this was gonna work. So here’s the final 🎥 video, just having some fun with it. I’ll update here whenever the real fox does come back. On a final note, I’m looking for (remote) jobs in these fields of AI now: - object detection - visual generative AI - 3D (nerfs + gaussian splats) So if you know anything let me know! My DMs are open 😊
2:05

My fox shooting garden defending AI robot is finally done and WORKING! 🤩 (Don’t worry it only shoots 💦 water) After months of slowly moving forward with each part I finished the last step to train a TensorFlow model on the footage of the 🦊 fox I collected hours of footage 📹 with the fox roaming around my garden, from this I labeled around 2000 images with the fox by hand ✋ Honestly, I was quite skeptical training the model was actually gonna work, maybe this was partly the reason I avoided working on this until the very end. If I couldn’t train a model to detect the fox, this whole robot would never be able to function properly. On the flipside though, with no previous experience in hardware or electronics there was a bit of a learning curve and I didn’t want to end up labeling thousands of images, training a TensorFlow model, only to fail on building the hardware. As I started building, I realized that mixing hardware and software adds quite another dimension to debugging things. At times I wasted hours debugging code in my IDE, only to realize the issue was somewhere in the electronics. Furthermore, combining this side project with a full time job and a young family, is not always easy. It can be quite frustrating, to know you only need 4 hours of concentrated effort for a small task, having to spread it out across a week of 20min increments. Then, a few months into the build I noticed the fox had stopped coming to my garden, in fact one day, I recorded her walking with 3 cute little 🐶 pups, and the next day I saw her moving out of my garden completely. Did she know I was building a robot? I had this strange mix of feelings, happy my garden was safe from poop and digging, happy she was safe with her pups, but how was I gonna finish this project if my robot had no fox to detect? For sure they would be back next year, I figured I could postpone the whole thing until next winter, but I also knew it was gonna be much harder to pick up momentum if I did let it sit there for six months. So I decided to keep working, hoping the fox would reappear,.. but she never did. As I finished labeling the footage and started training my model, I could finally see the mAP results, quantifying the precision of my object detection model. It was measuring at 78% across different metrics on detecting my fox. I quickly ran the model on some of the video footage I got from my fox. Inference speed took a hit, but it did a near perfect job detecting the fox, even when she was deep down in the grass or wizzing past in a motion blur. It took me by surprise how well it worked. With the default model I had to drop my confidence threshold way down to 15%, to recognize the fox as 🦜“bird” in one or two frames, with my custom model it followed the fox all the way down to the back of the garden! Still this didn’t solve the issue of there being no actual fox in my garden and how was I gonna wrap this project in a short timeframe. I played with the idea of putting a fox toy 🧸 on an RC 🚗 car, or borrowing a dog to run around the garden to test. Friends suggested I run around the garden in a fox costume.. what a ridiculous idea. I wasn’t really feeling the idea of running around the garden in a floppy cloth fox 🎭 costume, but had a look anyway. I came across these self inflating costumes. This actually could be perfect. Since it’s inflated, it would hold its shape super well, making it much easier to label, train and be recognized by my robot. So I got the costume and shot a time lapse of myself as a fox walking around the garden. I labeled it to around 600 images. Ran the model training again and got a mAP result of 82%. This was even better than my real fox! At this point I knew this was gonna work. So here’s the final 🎥 video, just having some fun with it. I’ll update here whenever the real fox does come back. On a final note, I’m looking for (remote) jobs in these fields of AI now: - object detection - visual generative AI - 3D (nerfs + gaussian splats) So if you know anything let me know! My DMs are open 😊

Jeroen Pixel

55,797 Aufrufe • vor 2 Jahren

A Fiscal Crisis Is Coming By 2030 And We Have Both Republicans And Democrats To Blame In my recent appearance on Thoughtful Money with our friend Adam Taggart , we unpacked the #math we use to project a US fiscal crisis by 2030 and how both Democrats and the GOP are perpetuating that outcome with socialist policies. If you are still a staunch Democrat or hardcore Republican after watching this, just know that you are dooming our children to a lifetime of slavery. For the rest of you, thanks in advance for ditching the Fox News/Truth Social/MSNBC/CNN propaganda so we can start developing solutions #together. ❤ Please like and repost if you’ve found this PSA helpful. Thank you! P.S. Link to full video:
14:17

A Fiscal Crisis Is Coming By 2030 And We Have Both Republicans And Democrats To Blame In my recent appearance on Thoughtful Money with our friend Adam Taggart , we unpacked the #math we use to project a US fiscal crisis by 2030 and how both Democrats and the GOP are perpetuating that outcome with socialist policies. If you are still a staunch Democrat or hardcore Republican after watching this, just know that you are dooming our children to a lifetime of slavery. For the rest of you, thanks in advance for ditching the Fox News/Truth Social/MSNBC/CNN propaganda so we can start developing solutions #together. ❤ Please like and repost if you’ve found this PSA helpful. Thank you! P.S. Link to full video:

Darius Dale

123,672 Aufrufe • vor 2 Jahren